Week 1, 2
N-grams and document classification.
- Read Chapter 1 and Sections 4.1-4.3 of the textbook.
- Take a look at 4.5 if you haven't yet
- Document Classification
- Reports due by class time on Monday, September 29.
Please submit via HSP.
Week 3
Minimum edit distance and spelling suggestions
- Read Sections 3.9-3.11.
- 3.9 just for interest, 3.10-11 for the new problem
- Document Classification Redux
- Send results by 11:59 PM Thursday, 10/2.
- Spelling Recommendations
- Reports will be given in class on Wednesday, October 8.
Week 4
Parsing
- Read Sections 12.1-4 and 13.1-4.
- The Earley Algorithm is discussed in 13.4
- A Parser
- No reports. Due 8:30 AM Friday, October 17.
Weeks 6, 7
Hidden Markov Models
- Read Sections 5.1-5.5 and 5.7.
- Read by Oct 27.
- Read Sections 6.1-6.5.
- Read by Oct 31.
- A Part-of-Speech Tagger
- Code, data, and written reports due 5:00 PM Wednesday, November 5.
Reports will be given in class Friday, November 7.
Week 8
Semantics, etc.
- Read Sections 18.1-3.
- Read by Nov 12.
- NLP Tools
- Reports will be given in class Wednesday, November 12.
The end
Wordnet, feature structures, and the final exam
- Read Sections 15.1-3.
- Read by Nov 17.
- The exam
- Due by 5:00 PM Monday, November 24.